© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12288
    Prev
    Next
    INDEX
    Explanations

    represent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rappresent
    -0.52
     propOrder
    -0.50
    Попис
    -0.47
    IntoConstraints
    -0.47
    kript
    -0.46
     REPRESENT
    -0.45
     Corintios
    -0.45
    piram
    -0.45
     represent
    -0.45
     TextInput
    -0.43
    POSITIVE LOGITS
    findpost
    0.71
    ubehör
    0.71
     peasants
    0.66
     Efq
    0.65
     Hindus
    0.64
     Britons
    0.62
     Mexicans
    0.60
     Normdatei
    0.59
     negroes
    0.59
     peasant
    0.58
    Activations Density 0.005%

    No Known Activations